As all of industry undergoes reinvention toward Digital Transformation during the next five to ten years, the key to success will be to invest in the right technology at the right time, and to redefine business processes while enabling people to better perform their jobs. In no industry is this more critical than within oil and gas. Faced with volatile prices that are just rebounding from near-record lows, safety pressures, increasing regulatory burdens and regional skilled labor pressures, all identified in the LNS Research Spotlight Why APM Is Critical to Operational Excellence in the Oil & Gas Industries, the oil and gas sector has a number of additional incentives to invest in the pursuit of Digital Transformation despite margin pressures and capital constraints.
The key enabling technology for Digital Transformation in the near term is the rapid growth in the Industrial Internet of Things (IIoT), which is driving new approaches to both Big Data and predictive analytics. The oil and gas industry is no stranger to digital technology—having undergone the first iteration of the “digital” with the advent of the digitization of geo-technical seismic data related to reserves/deposits. This has prepped the industry with an understanding of the value of data, and of how to use analytics to make sense of the wealth of information available with the onset of Smart Connected Assets. As the second wave of digitization takes hold with the IIoT, no industry has as much experience or better motivation to take advantage of what the IIoT offers, as equipment ranging from compressors, turbines, and other oil field and gas transmission equipment becomes smarter.
The New Digital Transformation of Oil and Gas
If the Digital Oil Field of the 2000s was the first wave of digitization, then the changes wrought by Industrie 4.0—or Smart Manufacturing, or just simply Digital Transformation—are the next generation. This reshaping of industry, driven by the IIoT, cloud technology, mobility, Big Data, and predictive analytics, will start with the addition of value-added services based on better information about asset performance, transition to OEMs delivering full lifecycle support and ultimately, in some instances, the selling of capacity instead of capital, such as selling CFH of gas moved instead of the compressor itself.
LNS Research already sees users investing in the IIoT today (see chart), with more than half of the oil and gas companies that are deploying IIoT-enabled technology using it for remote monitoring. Asset reliability and energy effiency round out the top three non-product use cases.
What Are the Top IIoT Use Cases Your Company is Pursuing Today?
What this means for the oil and gas industry is that the ability to use remote monitoring has already become the dominant application for the more than one-third of the industry that has already seen value in IIoT technology investment. In fact, remote monitoring has become so entrenched that it remains the number one investment area for those firms that are looking for IIoT use cases in the next year, and this applies across all sectors of the industry—upstream, midstream and downstream.
Turning Remote Monitoring Into Hard Dollar Savings
The old IT axiom is that information isn’t worth anything until you do something with it. This is certainly true when it comes to remote monitoring. Advances in cloud technology, Big Data and the IIoT, coupled with the evolution of self-learning systems, make new capabilities feasible today, unlike in the past where highly engineered and therefore expensive dedicated solutions were required. With the exponential growth of process and asset information, the quality of the predictions is only going to improve. The power of predictive analytics extends beyond just asset health management but to overall operation performance management as well. By combining current operating needs with equipment capabilities and customer requirements, true Operational Excellence is achievable by not just improving reliability and reducing downtime, but by improving production and throughput too.
Both condition-based maintenance (CBM) and reliability-centered maintenance (RCM) can leverage real-time information from sensors on operation equipment to provide timely and actionable warnings about deteriorating conditions that require attention to avoid catastrophic failures and unplanned downtime. These are well-established APM use cases for predictive analytics. As the volume of information about operation conditions increases thanks to the broader deployment of IIoT technology, better and better decisions are possible. We can move from descriptive or historical analysis of what happened to predictive analysis about what will happen to ultimately prescriptive analysis that can tell not just what will happen and when it will happen, but what we should do to preclude it from happening.
However, as we move toward autonomous assets that enable new business models, we shouldn’t lose sight of the fact that remote monitoring is more affordable today that it has ever been—even with remote assets that have limited bandwidth connectivity—thanks to IIoT innovations. And the savings from the avoidance of just one catastrophic failure can be in the millions of dollars in lost product, cleanup costs, and non-compliance penalties.